Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    organizations and standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    стич
    -0.06
     alo
    -0.06
    柱
    -0.06
    รวม
    -0.06
     DISCLAIMS
    -0.06
     calm
    -0.06
     PROGRAM
    -0.06
    xab
    -0.05
     durumunda
    -0.05
    isti
    -0.05
    POSITIVE LOGITS
    Rated
    0.08
    公
    0.07
     SEC
    0.07
     USDA
    0.06
     Journalism
    0.06
     fout
    0.06
    ฒ
    0.06
    ท
    0.06
    AB
    0.06
    .textAlignment
    0.06
    Act Density 0.031%

    No Known Activations